Merge tag 'dma-mapping-4.21' of git://git.infradead.org/users/hch/dma-mapping

Pull DMA mapping updates from Christoph Hellwig:
 "A huge update this time, but a lot of that is just consolidating or
  removing code:

   - provide a common DMA_MAPPING_ERROR definition and avoid indirect
     calls for dma_map_* error checking

   - use direct calls for the DMA direct mapping case, avoiding huge
     retpoline overhead for high performance workloads

   - merge the swiotlb dma_map_ops into dma-direct

   - provide a generic remapping DMA consistent allocator for
     architectures that have devices that perform DMA that is not cache
     coherent. Based on the existing arm64 implementation and also used
     for csky now.

   - improve the dma-debug infrastructure, including dynamic allocation
     of entries (Robin Murphy)

   - default to providing chaining scatterlist everywhere, with opt-outs
     for the few architectures (alpha, parisc, most arm32 variants) that
     can't cope with it

   - misc sparc32 dma-related cleanups

   - remove the dma_mark_clean arch hook used by swiotlb on ia64 and
     replace it with the generic noncoherent infrastructure

   - fix the return type of dma_set_max_seg_size (Niklas Söderlund)

   - move the dummy dma ops for not DMA capable devices from arm64 to
     common code (Robin Murphy)

   - ensure dma_alloc_coherent returns zeroed memory to avoid kernel
     data leaks through userspace. We already did this for most common
     architectures, but this ensures we do it everywhere.
     dma_zalloc_coherent has been deprecated and can hopefully be
     removed after -rc1 with a coccinelle script"

* tag 'dma-mapping-4.21' of git://git.infradead.org/users/hch/dma-mapping: (73 commits)
  dma-mapping: fix inverted logic in dma_supported
  dma-mapping: deprecate dma_zalloc_coherent
  dma-mapping: zero memory returned from dma_alloc_*
  sparc/iommu: fix ->map_sg return value
  sparc/io-unit: fix ->map_sg return value
  arm64: default to the direct mapping in get_arch_dma_ops
  PCI: Remove unused attr variable in pci_dma_configure
  ia64: only select ARCH_HAS_DMA_COHERENT_TO_PFN if swiotlb is enabled
  dma-mapping: bypass indirect calls for dma-direct
  vmd: use the proper dma_* APIs instead of direct methods calls
  dma-direct: merge swiotlb_dma_ops into the dma_direct code
  dma-direct: use dma_direct_map_page to implement dma_direct_map_sg
  dma-direct: improve addressability error reporting
  swiotlb: remove dma_mark_clean
  swiotlb: remove SWIOTLB_MAP_ERROR
  ACPI / scan: Refactor _CCA enforcement
  dma-mapping: factor out dummy DMA ops
  dma-mapping: always build the direct mapping code
  dma-mapping: move dma_cache_sync out of line
  dma-mapping: move various slow path functions out of line
  ...

1 files changed, 54 insertions, 26 deletions

diff --git a/arch/sparc/mm/io-unit.c b/arch/sparc/mm/io-unit.c
index c8cb27d3ea75..f770ee7229d8 100644
--- a/arch/sparc/mm/io-unit.c
+++ b/arch/sparc/mm/io-unit.c
@@ -12,7 +12,7 @@
 #include <linux/mm.h>
 #include <linux/highmem.h>	/* pte_offset_map => kmap_atomic */
 #include <linux/bitops.h>
-#include <linux/scatterlist.h>
+#include <linux/dma-mapping.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
 
@@ -140,34 +140,44 @@ nexti:	scan = find_next_zero_bit(iounit->bmap, limit, scan);
 	return vaddr;
 }
 
-static __u32 iounit_get_scsi_one(struct device *dev, char *vaddr, unsigned long len)
+static dma_addr_t iounit_map_page(struct device *dev, struct page *page,
+		unsigned long offset, size_t len, enum dma_data_direction dir,
+		unsigned long attrs)
 {
+	void *vaddr = page_address(page) + offset;
 	struct iounit_struct *iounit = dev->archdata.iommu;
 	unsigned long ret, flags;
 	
+	/* XXX So what is maxphys for us and how do drivers know it? */
+	if (!len || len > 256 * 1024)
+		return DMA_MAPPING_ERROR;
+
 	spin_lock_irqsave(&iounit->lock, flags);
 	ret = iounit_get_area(iounit, (unsigned long)vaddr, len);
 	spin_unlock_irqrestore(&iounit->lock, flags);
 	return ret;
 }
 
-static void iounit_get_scsi_sgl(struct device *dev, struct scatterlist *sg, int sz)
+static int iounit_map_sg(struct device *dev, struct scatterlist *sgl, int nents,
+		enum dma_data_direction dir, unsigned long attrs)
 {
 	struct iounit_struct *iounit = dev->archdata.iommu;
+	struct scatterlist *sg;
 	unsigned long flags;
+	int i;
 
 	/* FIXME: Cache some resolved pages - often several sg entries are to the same page */
 	spin_lock_irqsave(&iounit->lock, flags);
-	while (sz != 0) {
-		--sz;
+	for_each_sg(sgl, sg, nents, i) {
 		sg->dma_address = iounit_get_area(iounit, (unsigned long) sg_virt(sg), sg->length);
 		sg->dma_length = sg->length;
-		sg = sg_next(sg);
 	}
 	spin_unlock_irqrestore(&iounit->lock, flags);
+	return nents;
 }
 
-static void iounit_release_scsi_one(struct device *dev, __u32 vaddr, unsigned long len)
+static void iounit_unmap_page(struct device *dev, dma_addr_t vaddr, size_t len,
+		enum dma_data_direction dir, unsigned long attrs)
 {
 	struct iounit_struct *iounit = dev->archdata.iommu;
 	unsigned long flags;
@@ -181,34 +191,47 @@ static void iounit_release_scsi_one(struct device *dev, __u32 vaddr, unsigned lo
 	spin_unlock_irqrestore(&iounit->lock, flags);
 }
 
-static void iounit_release_scsi_sgl(struct device *dev, struct scatterlist *sg, int sz)
+static void iounit_unmap_sg(struct device *dev, struct scatterlist *sgl,
+		int nents, enum dma_data_direction dir, unsigned long attrs)
 {
 	struct iounit_struct *iounit = dev->archdata.iommu;
-	unsigned long flags;
-	unsigned long vaddr, len;
+	unsigned long flags, vaddr, len;
+	struct scatterlist *sg;
+	int i;
 
 	spin_lock_irqsave(&iounit->lock, flags);
-	while (sz != 0) {
-		--sz;
+	for_each_sg(sgl, sg, nents, i) {
 		len = ((sg->dma_address & ~PAGE_MASK) + sg->length + (PAGE_SIZE-1)) >> PAGE_SHIFT;
 		vaddr = (sg->dma_address - IOUNIT_DMA_BASE) >> PAGE_SHIFT;
 		IOD(("iounit_release %08lx-%08lx\n", (long)vaddr, (long)len+vaddr));
 		for (len += vaddr; vaddr < len; vaddr++)
 			clear_bit(vaddr, iounit->bmap);
-		sg = sg_next(sg);
 	}
 	spin_unlock_irqrestore(&iounit->lock, flags);
 }
 
 #ifdef CONFIG_SBUS
-static int iounit_map_dma_area(struct device *dev, dma_addr_t *pba, unsigned long va, unsigned long addr, int len)
+static void *iounit_alloc(struct device *dev, size_t len,
+		dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
 {
 	struct iounit_struct *iounit = dev->archdata.iommu;
-	unsigned long page, end;
+	unsigned long va, addr, page, end, ret;
 	pgprot_t dvma_prot;
 	iopte_t __iomem *iopte;
 
-	*pba = addr;
+	/* XXX So what is maxphys for us and how do drivers know it? */
+	if (!len || len > 256 * 1024)
+		return NULL;
+
+	len = PAGE_ALIGN(len);
+	va = __get_free_pages(gfp | __GFP_ZERO, get_order(len));
+	if (!va)
+		return NULL;
+
+	addr = ret = sparc_dma_alloc_resource(dev, len);
+	if (!addr)
+		goto out_free_pages;
+	*dma_handle = addr;
 
 	dvma_prot = __pgprot(SRMMU_CACHE | SRMMU_ET_PTE | SRMMU_PRIV);
 	end = PAGE_ALIGN((addr + len));
@@ -237,27 +260,32 @@ static int iounit_map_dma_area(struct device *dev, dma_addr_t *pba, unsigned lon
 	flush_cache_all();
 	flush_tlb_all();
 
-	return 0;
+	return (void *)ret;
+
+out_free_pages:
+	free_pages(va, get_order(len));
+	return NULL;
 }
 
-static void iounit_unmap_dma_area(struct device *dev, unsigned long addr, int len)
+static void iounit_free(struct device *dev, size_t size, void *cpu_addr,
+		dma_addr_t dma_addr, unsigned long attrs)
 {
 	/* XXX Somebody please fill this in */
 }
 #endif
 
-static const struct sparc32_dma_ops iounit_dma_ops = {
-	.get_scsi_one		= iounit_get_scsi_one,
-	.get_scsi_sgl		= iounit_get_scsi_sgl,
-	.release_scsi_one	= iounit_release_scsi_one,
-	.release_scsi_sgl	= iounit_release_scsi_sgl,
+static const struct dma_map_ops iounit_dma_ops = {
 #ifdef CONFIG_SBUS
-	.map_dma_area		= iounit_map_dma_area,
-	.unmap_dma_area		= iounit_unmap_dma_area,
+	.alloc			= iounit_alloc,
+	.free			= iounit_free,
 #endif
+	.map_page		= iounit_map_page,
+	.unmap_page		= iounit_unmap_page,
+	.map_sg			= iounit_map_sg,
+	.unmap_sg		= iounit_unmap_sg,
 };
 
 void __init ld_mmu_iounit(void)
 {
-	sparc32_dma_ops = &iounit_dma_ops;
+	dma_ops = &iounit_dma_ops;
 }